Wood Science and Technology

, Volume 52, Issue 5, pp 1195–1211 | Cite as

Moisture content recognition for wood chips in pile using supervised classification

  • Hela Daassi-Gnaba
  • Yacine OussarEmail author
  • Maria Merlan
  • Thierry Ditchi
  • Emmanuel Géron
  • Stéphane Holé


Wood chips moisture content (MC) is a key parameter for controlling the biofuel product qualities and properties. Since no knowledge-based model is available to recognize MC, machine learning methods are promising techniques to design black-box models for MC prediction or recognition. As wood permittivity strongly changes in the presence of water, an electromagnetic module is used to probe the reflectivity of wood chip piles. In the present paper, the recognition of three wood chip piles of different MC categories is performed using support vector machines (SVMs). SVM-recursive feature elimination is implemented to rank and select reflection coefficients to design optimized linear SVM classifiers that attribute MC class of wood chips in a pile. Experiments show that the proposed approach is effective and requires a limited computational power. The global classification performance exceeds 95%.



  1. Bogosanovic M, Al Anbuky A, Emms GW (2010) Overview and comparison of microwave noncontact wood measurement techniques. J Wood Sci 56:357–365CrossRefGoogle Scholar
  2. Chen S, Billings SA, Luo W (1989) Orthogonal least squares methods and their application to non-linear system identification. Int J Control 50(5):1873–1896CrossRefGoogle Scholar
  3. Cristianini N, Shawe-Taylor J (2000) Support vector machines and other kernel-based learning methods. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  4. Daassi-Gnaba H, Oussar Y (2012) Enhanced emotion recognition by feature selection to animate a talking head. In: Proceedings of the 20th European symposium on artificial neural networks, computational intelligence and machine learning (ESANN), Bruges, Belgium, pp 513–518Google Scholar
  5. Daassi-Gnaba H, Oussar Y (2015) External vs. internal svm-rfe: the svm-rfe method revisited and applied to emotion recognition. Neural Netw World 25(1):75–91CrossRefGoogle Scholar
  6. Daassi-Gnaba H, Oussar Y, Merlan M, Ditchi T, Géron E, Holé S (2017) Wood moisture content prediction using feature selection techniques and a kernel method. Neurocomputing 237:79–91CrossRefGoogle Scholar
  7. Daian G, Taube A, Birnboim A, Shramkov Y, Daian M (2005) Measuring the dielectric properties of wood at microwave frequencies. Wood Sci Technol 39:215–223CrossRefGoogle Scholar
  8. Daian G, Taube A, Birnboim A, Daian M, Shramkov Y (2006) Modeling the dielectric properties of wood. Wood Sci Technol 40:237–246CrossRefGoogle Scholar
  9. Gu IYH, Andersson H, Vicen R (2010) Wood defect classification based on image analysis and support vector machines. Wood Sci Technol 44:693–704CrossRefGoogle Scholar
  10. Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182Google Scholar
  11. Guyon I, Weston J, Barnhill S, Vapnik V (2002) Gene selection for cancer classification using support vector machines. Mach Learn 46(1–3):389–422CrossRefGoogle Scholar
  12. Hartmann H, Böhm T (2000) Rapid moisture content determination of wood chips—results from comparative trials. In: Proceedings of the first world conference on biomass for energy and industry, James & James Ltd., Sevilla, Spain, pp 571–574Google Scholar
  13. Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning. Springer, New YorkCrossRefGoogle Scholar
  14. Jensen P, Hartmann H, Böhm T, Temmerman M, Rabier F, Morsing M (2006) Moisture content determination in solid biofuels by dielectric and NIR reflection methods. Biomass Bioenergy 30(11):935–943CrossRefGoogle Scholar
  15. Jun C, Jiawei Z, Liping S (2009) Comparison on prediction wood moisture content using ARIMA and improved neural networks. In: International conference on computational intelligence for measurement systems and applications (CIMSA). IEEE, Hong Kong, China, pp 148–152Google Scholar
  16. King RJ, James WL, Yen YY (1985) A microwave method for measuring moisture content, density and grain angle of wood. United States Department of Agriculture. Research Note FPL-0250, Forest Products Laboratory, MadisonGoogle Scholar
  17. Krajnc N (2015) Wood fuels handbook. Food and agriculture organization of the United Nations, PristinaGoogle Scholar
  18. Kupfer K (2005) Electromagnetic aquametry: electromagnetic wave interaction with water and moist substances. Springer, BerlinCrossRefGoogle Scholar
  19. Lee Y, Lin Y, Wahba G (2004) Multicategory support vector machines: theory and application to the classification of microarray data and satellite radiance data. J Am Stat Assoc 99(465):67–81CrossRefGoogle Scholar
  20. Mabire P, Mayer A, Holé S, Ditchi T, Géron E, Mokthari Z (2015) Mesure nondestructive du taux d’humidité d’un matériau (A non-destructive measurement technique of the moisture content of a material). Patent FR1552032Google Scholar
  21. Manzano-Agugliaro F, Alcayde A, Montoya FG, Zapata-Sierra A, Gil C (2013) Scientific production of renewable energies worldwide: an overview. Renew Sustain Energy Rev 18(1):134–143CrossRefGoogle Scholar
  22. Merlan M, Ditchi T, Holé S, Oussar Y, Lucas J, Géron E (2015a) Système électromagnétique de mesure de l’humidité de plaquettes forestières (Moisture content measurement in wood chips using electromagnetic waves). In: Journées Scientifiques de l’Union Radio-scientifique Internationale, Paris, FranceGoogle Scholar
  23. Merlan M, Ditchi T, Lucas J, Géron E, Oussar Y, Holé S (2015b) Electromagnetic system to determine the moisture content of wood chips. In: Third international congress on energy efficiency and energy related materials, Oludeniz, Fethiye/Mugla, TurkeyGoogle Scholar
  24. Mora CR, Schimleck LR (2010) Kernel regression methods for the prediction of wood properties of pinus taeda using near infrared spectroscopy. Wood Sci Technol 44:561–578CrossRefGoogle Scholar
  25. Nyström J, Dahlquist E (2004) Methods for determination of moisture content in woodchips for power plants a review. Fuel 83(7–8):773–779CrossRefGoogle Scholar
  26. Nyström J, Thorin E, Backa SO, Dahlquist E (2005) Moisture content measurements on sawdust with radio frequency spectroscopy. In: American Society of mechanical engineers (ASME) power conference. Illinois, USA, Chicago, pp 697–702Google Scholar
  27. Oussar Y, Ahriz I, Denby B, Dreyfus G (2011) Indoor localization based on cellular telephony rssi fingerprints containing very large numbers of carriers. EURASIP J Wirel Commun Netw 2011(1):1–14CrossRefGoogle Scholar
  28. Samuelsson R, Burvall J, Jirjis R (2006) Comparison of different methods for the determination of moisture content in biomass. Biomass Bioenergy 30(11):929–934CrossRefGoogle Scholar
  29. Schajer GS, Orhan FB (2006) Measurement of wood grain angle, moisture content and density using microwaves. Holz Roh Werkst 64:483–490CrossRefGoogle Scholar
  30. Wen S, Deng M, Inoue A (2012) Moisture content prediction of wood drying process using svm-based model. Int J Innov Comput Inf Control (ICIC Int) 8(6):4083–4093Google Scholar
  31. Weston J, Elisseeff A, Bakir G, Sinz F (2006) The spider 1.71 [software]. Accessed 01 Oct 2007
  32. Zhang D, Cao J, Sun L (2009) Soft sensor modeling of moisture content in drying process based on LSSVM. In: The ninth international conference on electronic measurement and instruments (ICEMI), IEEE, Beijing, China, pp 2-989–2-993Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Hela Daassi-Gnaba
    • 1
  • Yacine Oussar
    • 1
    Email author
  • Maria Merlan
    • 1
  • Thierry Ditchi
    • 1
  • Emmanuel Géron
    • 1
  • Stéphane Holé
    • 1
  1. 1.Laboratoire de Physique et d’Étude des Matériaux (LPEM)ESPCI Paris, PSL Research University, CNRS, Sorbonne UniversitéParisFrance

Personalised recommendations